Classifying machinery condition using oil samples and binary logistic regression

    Research output: Contribution to journalArticle

    21 Citations (Scopus)

    Abstract

    © 2015 Elsevier Ltd. All rights reserved. The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.
    Original languageEnglish
    Pages (from-to)316-325
    JournalMechanical Systems and Signal Processing
    Volume60-61
    Issue number1
    DOIs
    Publication statusPublished - 2015

    Fingerprint

    Machinery
    Logistics
    Support vector machines
    Neural networks
    Engines
    Condition monitoring
    Trucks
    Explosions
    Industry
    Health
    Oils

    Cite this

    @article{852f8e5a9cff46c7b7908b8e9f154034,
    title = "Classifying machinery condition using oil samples and binary logistic regression",
    abstract = "{\circledC} 2015 Elsevier Ltd. All rights reserved. The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically {"}black box{"} approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.",
    author = "J. Phillips and Edward Cripps and John Lau and Melinda Hodkiewicz",
    year = "2015",
    doi = "10.1016/j.ymssp.2014.12.020",
    language = "English",
    volume = "60-61",
    pages = "316--325",
    journal = "Mechanical Systems and Signal Processing",
    issn = "0888-3270",
    publisher = "Academic Press",
    number = "1",

    }

    TY - JOUR

    T1 - Classifying machinery condition using oil samples and binary logistic regression

    AU - Phillips, J.

    AU - Cripps, Edward

    AU - Lau, John

    AU - Hodkiewicz, Melinda

    PY - 2015

    Y1 - 2015

    N2 - © 2015 Elsevier Ltd. All rights reserved. The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

    AB - © 2015 Elsevier Ltd. All rights reserved. The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

    U2 - 10.1016/j.ymssp.2014.12.020

    DO - 10.1016/j.ymssp.2014.12.020

    M3 - Article

    VL - 60-61

    SP - 316

    EP - 325

    JO - Mechanical Systems and Signal Processing

    JF - Mechanical Systems and Signal Processing

    SN - 0888-3270

    IS - 1

    ER -